Inner Canthus Thermal Imaging for Distance-Independent Temperature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional thermal imaging systems for detecting the inner canthus of a human face are prone to errors due to distance-related attenuation and difficulty in accurately measuring temperature when individuals wear masks or face coverings, leading to inaccurate body temperature detection.
Innovation Solution
A method and system that compensates for distance-related attenuation by applying correction terms based on facial features, such as face width, to improve the accuracy of inner canthus temperature measurements using thermal imaging, and incorporates artificial neural networks for face and canthus detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional thermal imaging is used to detect inner canthus temperature, then the system is simple and easy to operate, but the measurement precision deteriorates due to distance-related attenuation
Solution Approach 1:
The patent applies parameter changes by introducing a distance correction term that adjusts the measured temperature based on the detected distance between the thermal imager and the inner canthus. The correction term is calculated as a function of distance and applied to compensate for attenuation, thereby maintaining measurement precision across varying distances without requiring complex hardware modifications
Solution Approach 2:
The patent replaces mechanical/physical measurement systems with an artificial neural network-based detection system. The neural network automatically detects the inner canthus position and calculates distance from thermal image data, substituting traditional mechanical measurement methods and enabling automated compensation without additional physical sensors
2Measurement precision
If the inner canthus is used for temperature detection, then body temperature can be approximated, but the measurement precision deteriorates when the person is wearing a mask or face covering
Solution Approach 1:
The patent uses feedback by having the artificial neural network continuously analyze the thermal image to detect the presence of masks or face coverings. When such obstructions are detected, the system adjusts its measurement strategy or applies appropriate corrections based on the detected conditions, thereby maintaining measurement accuracy despite the harmful factor
Solution Approach 2:
The system changes measurement parameters dynamically based on detected conditions. When a mask is detected, the neural network adjusts which facial regions are used for temperature measurement or applies correction factors specific to masked conditions, allowing accurate body temperature estimation even when the inner canthus is partially obscured
3Productivity
If the thermal imager is placed farther from the subject to accommodate crowded scenarios, then more people can be scanned, but the measurement precision deteriorates due to increased distance attenuation
Solution Approach 1:
The patent enables distance-independent measurement by introducing a correction term that is applied to the raw temperature measurement based on the detected distance. This allows the system to maintain measurement precision whether the subject is close or far away, thereby enabling high-productivity scanning in crowded scenarios without sacrificing accuracy
Solution Approach 2:
The patent adds the distance dimension to the temperature measurement process. By detecting distance as an additional parameter and using it to calculate a correction term, the system transforms a single-parameter measurement into a multi-parameter measurement that compensates for distance effects, enabling accurate measurements across varying distances
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides stable and accurate temperature measurements of the inner canthus, independent of distance, enabling reliable detection of elevated body temperatures even in crowded scenarios with varying distances and mask usage.
Implementation Method 1
thermal imaging systems are frequently used to detect the temperatures of various objects or persons in a scene
Data Source
AI summary
Various techniques are disclosed to provide for improved human body temperature detection using thermal images of an inner canthus. In one example, a method includes capturing a thermal image of a human being using a thermal imager. The method also includes detecting a face and an inner canthus of the human being in the thermal image using an artificial neural network. The method also includes determining a temperature measurement of the inner canthus using corresponding pixels of the thermal image. The method also includes determining a body temperature of the human being using the temperature measurement. Additional methods and systems are also provided.